David Chan, Austin Myers, Sudheendra Vijayanarasimhan, David A. Ross, J. Canny
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
If you ask a human to describe an image, they might do so in a thousand different ways. Image captioning models, on the other hand, are traditionally trained to generate a single "best" (most like a reference) caption. Unfortunately, doing so encourages captions that are informationally impoverished. Such captions often focus on only a subset of possible details, while ignoring other potentially useful information in the scene. In this work, we introduce a simple, yet novel, method: "Image Captioning by Committee Consensus" (IC 3 ), designed to generate a single caption that captures details from multiple viewpoints by sampling from the learned semantic space of a base captioning model, and carefully leveraging a large language model to synthesize these samples into a single comprehensive caption. Our evaluations show that humans rate captions produced by IC 3 more helpful than those produced by SOTA models more than two-thirds of the time, and IC 3 improves the performance of SOTA automated recall systems by up to 84%, outperforming single human-generated reference captions and indicating significant improvements over SOTA approaches for visual description. Code/Resources are available at https://davidmchan. github.io/caption-by-committee.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2302.01328")
get_code_for_paper("2302.01328")
have("2302.01328")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2302.01328.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2302.01328)
Connect an agent — have() is free.